Simple Multi-Layer Perceptron in GML
Fully-connected neural network scripts with backpropagation.
These scripts is free simplified version of https://marketplace.yoyogames.com/assets/9616/multi-layer-neural-network
This asset includes three different MLP versions:
Array and Grid are different how they store and calculate weights. Mini is similiar to Array, but it's more simplified. Grid-based MLP calculates faster than Array, but needs to be explicitly destroyed.
Included learning methods:
SGD is supervised learning algorithm, which uses backpropagation. SGD supports using minibatches. Mean Squared Error is only cost function included in this asset.
Genetic Algorithm here is just one simple way of implementing it. It includes 1) Selection, 2) Offsprings, 3) Mutations.
As these are just simplified versions of original scripts, I have not throughly tested these, and I don't quarantee working.